» Tag
machine-learning
185 postsFinetuning a Reasoning LLM with Supervised or Reinforcement Learning?
Critical insights on training data representation and loss management in LLM finetuning.
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
The v6.0 update of Sentence Transformers introduces MultiVectorEncoder for enhanced late interaction retrieval.
Benchmarking Cheap LLMs for Production Agent Traces
We benchmarked cheaper LLMs for production agent traces. The results were significant.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comHubmesh: Smart Planner for Multi-hop RAG Retrieval
Hubmesh is a Python library that improves multi-hop RAG retrieval quality. It integrates seamlessly with vector databases.
Stop Overengineering Your Agent Harness
Learn how to avoid overengineering in agent harness design. Discover fundamental principles and context management techniques.
Eval-Driven Development: Lessons from Evaluating GenAI at Scale
Airbnb prioritizes evaluation in Generative AI product development, sharing best practices for engineers.
Cactus Hybrid: Training Gemma 4 to Recognize Its Mistakes
Cactus has improved the Gemma 4 model to recognize its mistakes. The on-device model now provides reliable responses with confidence scores.
Apple Is the King of AI and Nobody Knows It
Apple stands as the leader in AI by 2026, as NVIDIA's dominance declines and Apple's strategies gain attention.
Building a Practical Taxonomy for AI World Models
A report addressing the definition and classification of world models. It offers important insights for engineers.
Building a Multimodal Vector Search Platform for Product Catalogs
How a recommendation team built a multimodal vector search platform with Qdrant, tuned HNSW settings, and optimized GPU usage for embedding millions of products.